Filters








211 Hits in 3.7 sec

DeepCluster: A General Clustering Framework Based on Deep Learning [chapter]

Kai Tian, Shuigeng Zhou, Jihong Guan
<span title="">2017</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this paper, we propose a general framework DeepCluster to integrate traditional clustering methods into deep learning (DL) models and adopt Alternating Direction of Multiplier Method (ADMM) to optimize  ...  Furthermore, it is a general and flexible framework that can employ different networks and clustering methods.  ...  Conclusion This paper presents a deep learning based clustering framework that simultaneously learns hidden features and does cluster assignment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-71246-8_49">doi:10.1007/978-3-319-71246-8_49</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n5tvvppsqfhvrfipqzeaglfcue">fatcat:n5tvvppsqfhvrfipqzeaglfcue</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190219182521/http://pdfs.semanticscholar.org/191a/eefc9b9251766880c37739ca323073a70af7.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/1a/191aeefc9b9251766880c37739ca323073a70af7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-71246-8_49"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Unsupervised Image Classification for Deep Representation Learning [article]

Weijie Chen and Shiliang Pu and Di Xie and Shicai Yang and Yilu Guo and Luojun Lin
<span title="2020-08-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext  ...  For detailed interpretation, we further analyze its relation with deep clustering and contrastive learning.  ...  -Our training framework is twice faster than DeepCluster since we do not need an extra forward pass to generate pseudo labels. 2 Related Work 2.1 Self-supervised learning Self-supervised learning is a  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.11480v2">arXiv:2006.11480v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/y73sgvo7k5cl7aixdeaduwydfa">fatcat:y73sgvo7k5cl7aixdeaduwydfa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200822032245/https://arxiv.org/pdf/2006.11480v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.11480v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels [article]

Ke Sun, Zhouchen Lin, Zhanxing Zhu
<span title="2020-02-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting  ...  on improving the generalization performance of GCNs on graphs with few labeled nodes.  ...  a more general framework on weakly supervised signals for a wide range of data types.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.11038v2">arXiv:1902.11038v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3chqp7uzlfhujggjtibyuoqfnm">fatcat:3chqp7uzlfhujggjtibyuoqfnm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321080129/https://arxiv.org/pdf/1902.11038v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.11038v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Domain-Agnostic Clustering with Self-Distillation [article]

Mohammed Adnan, Yani A. Ioannou, Chuan-Yung Tsai, Graham W. Taylor
<span title="2021-12-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a new self-distillation based algorithm for domain-agnostic clustering. Our method builds upon the existing deep clustering frameworks and requires no separate student model.  ...  However, most self-supervised and deep clustering techniques rely heavily on data augmentation, rendering them ineffective for many learning tasks where insufficient domain knowledge exists for performing  ...  [6] proposed MoCo, a dynamic dictionary-based framework for unsupervised learning of visual representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12170v2">arXiv:2111.12170v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yhql4342lzf65fazrlulriontu">fatcat:yhql4342lzf65fazrlulriontu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211230065656/https://arxiv.org/pdf/2111.12170v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/41/51/41519152dde1bb2b76bcf1e58c449d9e27d92012.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12170v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes

Ke Sun, Zhouchen Lin, Zhanxing Zhu
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting  ...  on improving the generalization performance of GCNs on graphs with few labeled nodes.  ...  a more general framework on weakly supervised signals for a wide range of data types.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.6048">doi:10.1609/aaai.v34i04.6048</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rg4rpoo4anh65inmnvq3jaicge">fatcat:rg4rpoo4anh65inmnvq3jaicge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103160040/https://aaai.org/ojs/index.php/AAAI/article/download/6048/5904" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/02/e4/02e41bce163a2b1d7def4931a36f83e256412e0f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.6048"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

DECAR: Deep Clustering for learning general-purpose Audio Representations [article]

Sreyan Ghosh and Ashish Seth and Sandesh V Katta and S. Umesh
<span title="2022-04-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce DECAR (DEep Clustering for learning general-purpose Audio Representations), a self-supervised pre-training approach for learning general-purpose audio representations.  ...  Our system is based on clustering: it utilizes an offline clustering step to produce pseudo-labels and trains the network with a classification loss supervised by these pseudo-labels.  ...  To alleviate the above problems, inspired by the DeepCluster framework in CV [1, 17] , we introduce DECAR: DEep Clustering for General-Purpose Audio Representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08895v3">arXiv:2110.08895v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6yszijdh75bdrmjf2lntsyqlrq">fatcat:6yszijdh75bdrmjf2lntsyqlrq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220520092936/https://arxiv.org/pdf/2110.08895v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/18/0e/180ef02e76e351f9645144d2c2e16c69399a0f5a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08895v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SHAPE Project Vision-e: Deep Tile Inspection

Rudy Melli, Eric Pascolo
<span title="2019-11-22">2019</span> <i title="Zenodo"> Zenodo </i> &nbsp;
We investigated Deep Learning technologies applied to clustering tiles using the DeepCluster approach and the good results we get, show us that this is the right way to reach the goal and to continue,  ...  starting from a study on the choice of input data.  ...  It obtains useful general-purpose visual features with a clustering framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3773749">doi:10.5281/zenodo.3773749</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jup5ul5evvbs3bd4c3rhogckri">fatcat:jup5ul5evvbs3bd4c3rhogckri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200501190247/https://zenodo.org/record/3773750/files/WP291.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/70/59/70590fe2270040ea64a4c04ac42532be4881f611.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3773749"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Deep Clustering for Unsupervised Learning of Visual Features [chapter]

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.  ...  Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision.  ...  [68] iteratively learn convnet features and clusters with a recurrent framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_9">doi:10.1007/978-3-030-01264-9_9</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m64sdogi4zapbih4m6moymhi4y">fatcat:m64sdogi4zapbih4m6moymhi4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180920144227/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Mathilde_Caron_Deep_Clustering_for_ECCV_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/28/1d/281ddda8661dcac5cf9c0868ab80ff2c9cd45ba1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization [chapter]

Turkay Kart, Wenjia Bai, Ben Glocker, Daniel Rueckert
<span title="">2021</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this work, we propose an unsupervised approach for automatically clustering and categorizing large-scale medical image datasets, with a focus on cardiac MR images, and without using any labels.  ...  Our method was able to create clusters with high purity and achieved over 0.99 cluster purity on these datasets.  ...  [1] implemented an ensemble method of deep clustering methods based on K-means clustering. Pathan et. al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-88210-5_26">doi:10.1007/978-3-030-88210-5_26</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j5aqnwlfvjbljkoy7cbijtkzbu">fatcat:j5aqnwlfvjbljkoy7cbijtkzbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211010002011/https://arxiv.org/pdf/2110.00109v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/de/31/de313c6bb4ab97c71e912bee866f9db38a5e61a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-88210-5_26"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Deep Clustering for Unsupervised Learning of Visual Features [article]

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze
<span title="2019-03-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.  ...  Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision.  ...  [21] iteratively learn convnet features and clusters with a recurrent framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.05520v2">arXiv:1807.05520v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bfkl2g4qafc7ldpp5mqsivedp4">fatcat:bfkl2g4qafc7ldpp5mqsivedp4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018224350/https://arxiv.org/pdf/1807.05520v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a4/fa/a4faba8a0a0342fd1bf11051bfc07c5644b2ec8a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.05520v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Short-term Road Traffic Prediction based on Deep Cluster at Large-scale Networks [article]

Lingyi Han, Kan Zheng, Long Zhao, Xianbin Wang, Xuemin Shen
<span title="2019-02-25">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Therefore, a framework combining with a deep clustering (DeepCluster) module is developed for STTP at largescale networks in this paper.  ...  The DeepCluster module is proposed to supervise the representation learning in a visualized way from the large unlabeled dataset.  ...  To address the issues of the raw data-based or hand-craft-based clustering methods, we use the deep representation learning for series clustering.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.09601v1">arXiv:1902.09601v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dfxlbonxbjepjgk67irl2lgwzu">fatcat:dfxlbonxbjepjgk67irl2lgwzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017044058/https://arxiv.org/pdf/1902.09601v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/16/8c/168c22412e1ec7590684e576f0f889533b48860a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.09601v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Deep Metric Learning via Auxiliary Rotation Loss [article]

Xuefei Cao, Bor-Chun Chen, Ser-Nam Lim
<span title="2019-11-16">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose to generate pseudo-labels for deep metric learning directly from clustering assignment and we introduce unsupervised deep metric learning (UDML) regularized by a self-supervision  ...  UDML-SS iteratively cluster embeddings using traditional clustering algorithm (e.g., k-means), and sampling training pairs based on the cluster assignment for metric learning, while optimizing self-supervised  ...  We propose a metric learning loss that is based on cluster assign- Rotation labels Figure 1 . Unsupervised metric learning with rotation-based self-supervision.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07072v1">arXiv:1911.07072v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hifiz62uxrclbjmionomczonoi">fatcat:hifiz62uxrclbjmionomczonoi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930061637/https://arxiv.org/pdf/1911.07072v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/60/bd/60bdc0d240eff528f6f5a183c7cb875a1aafa459.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07072v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo [article]

Shintaro Nishi, Takeaki Kadota, Seiichi Uchida
<span title="2021-06-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper analyzes a large number of logo images from the LLD-logo dataset, by recent deep learning-based techniques, to understand not only design trends of logo images and but also the correlation to  ...  Especially, we focus on three correlations between logo images and their text areas, between the text areas and the number of followers on Twitter, and between the logo images and the number of followers  ...  and the Text Area Ratio 5.1 Logo image clustering by DeepCluster [7] DeepCluster is a clustering technique with a representation learning function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00327v2">arXiv:2104.00327v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3owbjxkcwbdahhnirzl3fribhy">fatcat:3owbjxkcwbdahhnirzl3fribhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210702012251/https://arxiv.org/pdf/2104.00327v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/90/b3/90b385ca91025931e3e37d3dc30bdce259019ad0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00327v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Discovering New Intents with Deep Aligned Clustering [article]

Hanlei Zhang, Hua Xu, Ting-En Lin, Rui Lyu
<span title="2021-03-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data.  ...  They also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents.  ...  MPCK-means (Bilenko, Basu, and Mooney 2004) incorporates the metric-learning approach into PCK-means and combined the centroid-based methods and metric-based methods into a unified framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08987v7">arXiv:2012.08987v7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w444n65osjdldjds6qhkqresge">fatcat:w444n65osjdldjds6qhkqresge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201225055141/https://arxiv.org/pdf/2012.08987v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/aa/c8/aac8bc75962262309a83d96e32b50b97aff8e71e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08987v7" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Self-Supervised Learning by Cross-Modal Audio-Video Clustering [article]

Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran
<span title="2020-10-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Based on this intuition, we propose Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the  ...  Their intrinsic differences make cross-modal prediction a potentially more rewarding pretext task for self-supervised learning of video and audio representations compared to within-modality learning.  ...  There are different ways we can adapt the deep clustering framework to a multi-modal input.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12667v3">arXiv:1911.12667v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zryoizk3bnagfnplxxhlzbzura">fatcat:zryoizk3bnagfnplxxhlzbzura</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201030105500/https://arxiv.org/pdf/1911.12667v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b9/56/b956220d181c6dd294a36d42cd65dbecd82a2f57.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12667v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 211 results